tpae
Joined 15 years ago
Karma
290
Submissions
171
Member since
Dec 5
Recent submissions
Comment · 3 months ago
Comment · 3 months ago
Open source would make them an instant credible leader, major fumble (still can be fixed)
Comment · 4 months ago
I've been building native macOS harness called Osaurus https://osaurus.ai/
It's full featured with agent loop, gets work done locally.
It's open-source and Swift-based, we built our own inferencing engine since every other engine is based on Python. Check us out - https://github.com/osaurus-ai/osaurus
Looking for some feedback!
Comment · 8 months ago
just fixed it
Comment · 8 months ago
The framing here assumes you need to ship native to all 3 platforms to justify leaving Electron. You don't.
I've been building a native macOS AI client in Swift — it's 15MB, provider-agnostic, and open source: https://github.com/dinoki-ai/osaurus
Committing to one platform well beats a mediocre Electron wrapper on all three.
Comment · 9 months ago
You can check out my project here: https://github.com/dinoki-ai/osaurus
I'm focused on building it for the macOS ecosystem
Comment · 10 months ago
I'm working on https://github.com/dinoki-ai/osaurus, Native macOS LLM server with MCP support. Looking for more feedback!
Comment · 11 months ago
This looks cool. I actually created Tweaks - https://tweaks.io/
Comment · 11 months ago
I've been building with local AI, on Apple Silicon. It's only 8mb, but runs 30% faster than Ollama.
Comment · 1 year ago
Not yet, but can be supported in the future
Comment · 1 year ago
I just finished https://tweaks.io, it's open-source and MIT licensed. Let me know your thoughts!
Comment · 1 year ago
I'm working on Osaurus - https://github.com/dinoki-ai/osaurus, native, Apple Silicon–only local LLM server. Open Source + MIT-License
https://github.com/osaurus-ai/osaurus